AgentLoom

Name: AgentLoom
Author: linora-u

data-ai MCP Server

Simple, flexible workflow orchestration for multi-agent AI apps, with YAML configuration, runtime safety, observability, and resume support.

bylinora-u

Verified

data-aidata-ai

5 views33 stars2 forks

View on GitHub Homepage Docs

Why This Matters

Discovered via agent-topic:ai-agent and last synced 3mo ago.

Verified

Source: agent-topic:ai-agent
Stars: 33
Last synced: 3mo ago
Install: Check source

Install

Install instructions not detected yet

Check the source repository for the latest setup steps.

View source instructions

Tools

Resources

Prompts

Standard I/O

Transport

Available Tools (16)

repo_map

Repository architecture map generator.

Area

Implemented Capabilities

Skill

Purpose

Document

Description

Command

Purpose

Agent-as-Tool

Workers export as callable tools through `agent_function_schema`, with generated function signatures, required-input validation, docstrings, string results, and `.batch(tasks)`.

create-app

Generate an AgentLoom application scaffold.

unit_test_studio

Python pytest generation workflow.

update-skills

Keep development skills aligned with source and docs changes.

Application

What It Builds

workflow-review

Review Agent/Tool boundaries, orchestration contracts, and resilience design.

ai_quality_analysis

Multi-dimensional code review application.

shell-security

Configure shell execution safety policies.

create-skill

Create a custom AgentLoom skill.

codex_exec_demo

Local Codex Exec tool-call example.

Observability

Rich terminal logs, plain text file logs, per-step duration, cumulative/incremental token usage, task/subtask/agent context, and run archiving under `.logs/`.

Browse all MCP servers